© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 20964
    Prev
    Next
    INDEX
    Explanations

    words related to being untethered or unattached

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "adhere."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Americ
    -0.72
     haste
    -0.68
    Hispanic
    -0.68
     gent
    -0.62
    Times
    -0.60
     distressed
    -0.60
     Giuliani
    -0.58
     Garc
    -0.58
     Mex
    -0.56
    battle
    -0.56
    POSITIVE LOGITS
    hered
    1.30
    nesday
    0.86
    rake
    0.86
    vous
    0.85
    milo
    0.84
    vironment
    0.82
    ¿½
    0.80
    tsky
    0.79
    zik
    0.78
     destro
    0.78
    Activations Density 0.012%

    No Known Activations